Optic disk segmentation in retinal images using active contour model based on extended feature projection

Abstract

Accurate localization and segmentation of an optic disk (OD) is an important problem in the analysis of abnormality conditions such as optic disk shrinking/swelling, pale optic disk and glucoma. Hence, this paper proposes an automated fast and accurate OD localization and segmentation technique. In this work, OD localization is performed using the extended feature projection method (EFP) based on retinal vessel orientation and average intensity variance. Multiple OD candidate locations, obtained from OD localization technique (EFP), are used as the initialization points of the active contour model to detect the OD boundaries. Next, we use a decision tree based on the OD features such as the area of vessels, the brightness and the entropy to select the final OD candidate. The proposed technique has been tested on STARE dataset to evaluate comparative studies on the localization and segmentation of OD in retinal images. The accuracy of the OD localization is 90.12% with an average computing time of 13 seconds per image. The performance of the OD segmentation in terms of sensitivity is 74.62 % and positive predictive value is 60.22% with an average computing time of 20 seconds per image. The proposed approach improves the accuracy of conventional feature projection method by 12.34% and runs as quickly as the conventional one.